Automatic Acquisition of Basic Katakana Lexicon from a Given Corpus

Abstract. Katakana, Japanese phonogram mainly used for loan words, is a troublemaker in Japanese word segmentation. Since Katakana words are heavily domaindependent and there are many Katakana neologisms, it is almost impossible to construct and maintain Katakana word dictionary by hand. This paper proposes an automatic segmentation method of Japanese Katakana compounds, which makes it possible to construct precise and concise Katakana word dictionary automatically, given only a medium or large size of Japanese corpus of some domain.

• Type: Conference
• Year: 2005
• Where: IJCNLP
• Authors: Toshiaki Nakazawa, Daisuke Kawahara, Sadao Kurohashi
• Keywords: IJCNLP 2005, Japanese Katakana Compounds, Katakana Neologisms, Katakana Word, Natural Language Processing